From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
To: linux-kernel@vger.kernel.org
Cc: mingo@kernel.org, laijs@cn.fujitsu.com, dipankar@in.ibm.com,
akpm@linux-foundation.org, mathieu.desnoyers@efficios.com,
josh@joshtriplett.org, tglx@linutronix.de, peterz@infradead.org,
rostedt@goodmis.org, dhowells@redhat.com, edumazet@google.com,
dvhart@linux.intel.com, fweisbec@gmail.com, oleg@redhat.com,
bobby.prani@gmail.com,
"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Subject: [PATCH tip/core/rcu 06/13] rcutorture: Replace barriers with smp_store_release() and smp_load_acquire()
Date: Tue, 12 May 2015 15:58:06 -0700 [thread overview]
Message-ID: <1431471493-5431-6-git-send-email-paulmck@linux.vnet.ibm.com> (raw)
In-Reply-To: <1431471493-5431-1-git-send-email-paulmck@linux.vnet.ibm.com>
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
The rcutorture.c file uses several explicit memory barriers that can
easily be converted to smp_store_release() and smp_load_acquire(), which
improves maintainability and also improves performance a bit.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
kernel/rcu/rcutorture.c | 24 +++++++++++++-----------
1 file changed, 13 insertions(+), 11 deletions(-)
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 7294d605c481..90ff8dfc51e5 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -672,8 +672,8 @@ static void rcu_torture_boost_cb(struct rcu_head *head)
struct rcu_boost_inflight *rbip =
container_of(head, struct rcu_boost_inflight, rcu);
- smp_mb(); /* Ensure RCU-core accesses precede clearing ->inflight */
- rbip->inflight = 0;
+ /* Ensure RCU-core accesses precede clearing ->inflight */
+ smp_store_release(&rbip->inflight, 0);
}
static int rcu_torture_boost(void *arg)
@@ -710,9 +710,9 @@ static int rcu_torture_boost(void *arg)
call_rcu_time = jiffies;
while (ULONG_CMP_LT(jiffies, endtime)) {
/* If we don't have a callback in flight, post one. */
- if (!rbi.inflight) {
- smp_mb(); /* RCU core before ->inflight = 1. */
- rbi.inflight = 1;
+ if (!smp_load_acquire(&rbi.inflight)) {
+ /* RCU core before ->inflight = 1. */
+ smp_store_release(&rbi.inflight, 1);
call_rcu(&rbi.rcu, rcu_torture_boost_cb);
if (jiffies - call_rcu_time >
test_boost_duration * HZ - HZ / 2) {
@@ -751,11 +751,10 @@ checkwait: stutter_wait("rcu_torture_boost");
} while (!torture_must_stop());
/* Clean up and exit. */
- while (!kthread_should_stop() || rbi.inflight) {
+ while (!kthread_should_stop() || smp_load_acquire(&rbi.inflight)) {
torture_shutdown_absorb("rcu_torture_boost");
schedule_timeout_uninterruptible(1);
}
- smp_mb(); /* order accesses to ->inflight before stack-frame death. */
destroy_rcu_head_on_stack(&rbi.rcu);
torture_kthread_stopping("rcu_torture_boost");
return 0;
@@ -1413,12 +1412,15 @@ static int rcu_torture_barrier_cbs(void *arg)
do {
wait_event(barrier_cbs_wq[myid],
(newphase =
- READ_ONCE(barrier_phase)) != lastphase ||
+ smp_load_acquire(&barrier_phase)) != lastphase ||
torture_must_stop());
lastphase = newphase;
- smp_mb(); /* ensure barrier_phase load before ->call(). */
if (torture_must_stop())
break;
+ /*
+ * The above smp_load_acquire() ensures barrier_phase load
+ * is ordered before the folloiwng ->call().
+ */
cur_ops->call(&rcu, rcu_torture_barrier_cbf);
if (atomic_dec_and_test(&barrier_cbs_count))
wake_up(&barrier_wq);
@@ -1439,8 +1441,8 @@ static int rcu_torture_barrier(void *arg)
do {
atomic_set(&barrier_cbs_invoked, 0);
atomic_set(&barrier_cbs_count, n_barrier_cbs);
- smp_mb(); /* Ensure barrier_phase after prior assignments. */
- barrier_phase = !barrier_phase;
+ /* Ensure barrier_phase ordered after prior assignments. */
+ smp_store_release(&barrier_phase, !barrier_phase);
for (i = 0; i < n_barrier_cbs; i++)
wake_up(&barrier_cbs_wq[i]);
wait_event(barrier_wq,
--
1.8.1.5
next prev parent reply other threads:[~2015-05-12 22:59 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-05-12 22:57 [PATCH tip/core/rcu 0/13] Torture-test updates for 4.2 Paul E. McKenney
2015-05-12 22:58 ` [PATCH tip/core/rcu 01/13] locktorture: fix deadlock in 'rw_lock_irq' type Paul E. McKenney
2015-05-12 22:58 ` [PATCH tip/core/rcu 02/13] rcutorture: Exchange TREE03 and TREE04 geometries Paul E. McKenney
2015-05-12 22:58 ` [PATCH tip/core/rcu 03/13] rcutorture: Exchange TREE03 and TREE08 NR_CPUS, speed up CPU hotplug Paul E. McKenney
2015-05-12 22:58 ` [PATCH tip/core/rcu 04/13] rcutorture: Allow negative values of nreaders to oversubscribe Paul E. McKenney
2015-05-13 1:03 ` josh
2015-05-13 17:23 ` Paul E. McKenney
2015-05-12 22:58 ` [PATCH tip/core/rcu 05/13] locktorture: Change longdelay_us to longdelay_ms Paul E. McKenney
2015-05-12 22:58 ` Paul E. McKenney [this message]
2015-05-12 22:58 ` [PATCH tip/core/rcu 07/13] rcutorture: Test SRCU cleanup code path Paul E. McKenney
2015-05-12 22:58 ` [PATCH tip/core/rcu 08/13] rcutorture: TASKS_RCU set directly, so don't explicitly set it Paul E. McKenney
2015-05-12 22:58 ` [PATCH tip/core/rcu 09/13] rcutorture: Update configuration fragments for rcutree.rcu_fanout_exact Paul E. McKenney
2015-05-12 22:58 ` [PATCH tip/core/rcu 10/13] rcutorture: Make rcutorture scripts force RCU_EXPERT Paul E. McKenney
2015-05-12 22:58 ` [PATCH tip/core/rcu 11/13] rcutorture: Update TREE_RCU-kconfig.txt Paul E. McKenney
2015-05-13 1:06 ` josh
2015-05-13 17:28 ` Paul E. McKenney
2015-05-13 22:13 ` josh
2015-05-12 22:58 ` [PATCH tip/core/rcu 12/13] rcutorture: Display "make oldconfig" errors Paul E. McKenney
2015-05-12 22:58 ` [PATCH tip/core/rcu 13/13] rcutorture: Allow repetition factors in Kconfig-fragment lists Paul E. McKenney
2015-05-13 1:07 ` [PATCH tip/core/rcu 0/13] Torture-test updates for 4.2 josh
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1431471493-5431-6-git-send-email-paulmck@linux.vnet.ibm.com \
--to=paulmck@linux.vnet.ibm.com \
--cc=akpm@linux-foundation.org \
--cc=bobby.prani@gmail.com \
--cc=dhowells@redhat.com \
--cc=dipankar@in.ibm.com \
--cc=dvhart@linux.intel.com \
--cc=edumazet@google.com \
--cc=fweisbec@gmail.com \
--cc=josh@joshtriplett.org \
--cc=laijs@cn.fujitsu.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mathieu.desnoyers@efficios.com \
--cc=mingo@kernel.org \
--cc=oleg@redhat.com \
--cc=peterz@infradead.org \
--cc=rostedt@goodmis.org \
--cc=tglx@linutronix.de \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®